ClawHub

ChessMaster

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed chess-game integration that can play and monitor games autonomously using game-scoped tokens.

Install this only if you want an agent to keep playing ChessMaster games after a room is active. Keep agentToken values private, avoid logging or sharing them, request live move updates if you want visibility into moves, and clear stored room IDs and tokens when you want play to stop.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
94% confidence
Finding
The skill explicitly requires storing the `agentToken` and `roomId` in persistent memory or a database, which introduces unnecessary long-lived credential retention for a chess gameplay integration. Even if persistence is functionally useful for reconnecting, the documentation does not justify retention limits, minimization, or access controls, so compromise of agent memory/storage could expose active game credentials and enable unauthorized actions in rooms.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly instructs persistent storage of both `roomId` and `agentToken` in a file or database, but provides no guidance on secure storage, encryption, access controls, retention, or user disclosure. Persisting bearer tokens increases the blast radius of compromise because anyone who obtains the stored token can act as the agent against the chess platform until the token is revoked or expires.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The documentation instructs agents to store `agentToken` and `roomId` persistently but provides no warning that `agentToken` is effectively a bearer credential requiring secure treatment. This omission increases the chance that implementers will place tokens in plaintext memory stores, logs, or databases, making credential theft and session hijacking more likely.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal